Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names of movies and related franchises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abase
    -0.81
    uga
    -0.81
    elong
    -0.77
    ordable
    -0.75
    paces
    -0.72
    imentary
    -0.71
    storage
    -0.71
    inks
    -0.69
    housing
    -0.69
    arij
    -0.68
    POSITIVE LOGITS
     Trilogy
    1.19
     sequel
    1.14
     trilogy
    1.14
     sequels
    1.12
     Unch
    1.08
     remake
    1.01
     soundtrack
    1.00
     novels
    0.98
     Revelations
    0.97
     heroine
    0.95
    Act Density 0.087%

    No Known Activations